© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21199
    Prev
    Next
    INDEX
    Explanations

    for your / in [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iske
    -0.06
    çİ°å°Ĩæľīåħ³äºĭ项
    -0.06
    uxe
    -0.06
     à¹Ĩ
    -0.06
    verse
    -0.06
    atak
    -0.05
    ok
    -0.05
    æ´»åĬ¨çŃī
    -0.05
    sung
    -0.05
     confr
    -0.05
    POSITIVE LOGITS
    çķĮ
    0.06
    bourne
    0.05
    殿
    0.05
    ÃŃgu
    0.05
     Burg
    0.05
    å´İ
    0.05
    .bind
    0.05
     Hierbei
    0.05
    æ¯ıä½į
    0.05
    ÑģлÑĮ
    0.05
    Activations Density 0.220%

    No Known Activations